AI Video Craft Evaluator: Film, VFX & Performance

Marketframe; United States; Remote; USD 30,000 - 52,000; Part time

Job summary

Marketframe invites experienced film/theater and visual effects professionals to join a leading AI lab's cutting-edge research team. You will compare AI-generated videos, judging craft like lighting, framing, camera movement, texture, and continuity, providing concise, supervisor-style rationales.

Role requires a trained eye for detail, fluency in English, and the ability to contribute at least 20 hours per week on weekdays. Collaboration with other experts ensures evaluation data accuracy.

Qualifications

• Eye for detail with strong visual judgment.
• Excellent written communication skills.
• Fluent in English; second dubbing language a strong plus (French, Italian, German, Spanish, Portuguese, Korean or Hindi).
• Availability to engage reliably for at least 20 hours/week during weekdays.
• Ability to explain creative judgments clearly in supervisor-style dailies language.

Responsibilities

• Evaluate pairs of AI-generated videos from the same prompt and select the stronger result across craft axes.
• Write concise reasons for judgments highlighting what worked or broke.
• Verify prompts and delivered camera moves, framing, and performance.
• Participate in calibration rounds to maintain consistency across raters.
• Collaborate with other experts to ensure data accuracy.

Skills

Eye for detail

Strong written communication

English fluency

20 hours/week availability

Clear judgment explanations

Education

Film/theater program training

4+ years of practical experience or 2+ years with releases

Job description

Marketframe invites experienced film/theater and visual effects professionals to join a leading AI lab's cutting-edge research team. You will compare AI-generated videos, judging craft like lighting, framing, camera movement, texture, and continuity, providing concise, supervisor-style rationales.

Role requires a trained eye for detail, fluency in English, and the ability to contribute at least 20 hours per week on weekdays. Collaboration with other experts ensures evaluation data accuracy.